One-dimensional Tensor Network Recovery

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Ziang, Lu, Jianfeng, Zhang, Anru R.
Format: Preprint
Published: 2022
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913295973220352
author Chen, Ziang
Lu, Jianfeng
Zhang, Anru R.
author_facet Chen, Ziang
Lu, Jianfeng
Zhang, Anru R.
contents We study the recovery of the underlying graphs or permutations for tensors in the tensor ring or tensor train format. Our proposed algorithms compare the matricization ranks after down-sampling, whose complexity is $O(d\log d)$ for $d$-th order tensors. We prove that our algorithms can almost surely recover the correct graph or permutation when tensor entries can be observed without noise. We further establish the robustness of our algorithms against observational noise. The theoretical results are validated by numerical experiments.
format Preprint
id arxiv_https___arxiv_org_abs_2207_10665
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle One-dimensional Tensor Network Recovery
Chen, Ziang
Lu, Jianfeng
Zhang, Anru R.
Numerical Analysis
Statistics Theory
We study the recovery of the underlying graphs or permutations for tensors in the tensor ring or tensor train format. Our proposed algorithms compare the matricization ranks after down-sampling, whose complexity is $O(d\log d)$ for $d$-th order tensors. We prove that our algorithms can almost surely recover the correct graph or permutation when tensor entries can be observed without noise. We further establish the robustness of our algorithms against observational noise. The theoretical results are validated by numerical experiments.
title One-dimensional Tensor Network Recovery
topic Numerical Analysis
Statistics Theory
url https://arxiv.org/abs/2207.10665